© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 151086
    Prev
    Next
    INDEX
    Explanations

    if you

    np_acts-logits-general · gemini-2.5-flash-lite

    introduces definitions or explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    יה
    0.42
    uzz
    0.41
    zele
    0.41
    hiqdev
    0.40
     PRE
    0.40
    👀
    0.39
    vous
    0.39
     cartera
    0.39
     ventricle
    0.38
    던
    0.38
    POSITIVE LOGITS
     recitation
    0.50
     некоторы
    0.50
     ബ
    0.49
     ภาษา
    0.48
     студент
    0.48
     儿童
    0.48
     函数
    0.47
     теат
    0.46
     защита
    0.46
     акт
    0.46
    Activations Density 0.000%

    No Known Activations